How to Use the New Relic AI (LLM Observability) MCP in CrewAI

Q: Does New Relic AI (LLM Observability) help CrewAI with cost control?

It does. You can program a crew member to monitor queryllmcosts and halt non-essential research tasks if budget limits are hit. It provides a safety net for your operations.

Deploy an autonomous monitoring crew using New Relic AI (LLM Observability) to manage and scale your CrewAI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect New Relic AI (LLM Observability) MCP to CrewAI

Create your Vinkius account to connect New Relic AI (LLM Observability) to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup New Relic AI (LLM Observability) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized monitoring for CrewAI crews

Assign a dedicated monitor agent to call `query_llm_latency` and `query_llm_costs` across your entire crew. It provides a bird's-eye view of how your multi-agent teams perform together. This allows your moderator agent to make informed decisions about scaling or reallocating tasks. You get a clear picture of resource usage without manual intervention.

Automated feedback loops for agents

Use `query_llm_feedback` to let your agents learn from past interactions by reviewing user satisfaction scores. It enables your crew to adjust their approach based on previous results. This creates a closed-loop system where agents improve their own performance. You define the thresholds, and the agents handle the rest.

System-wide error auditing

The `list_apm_apps` and `query_llm_errors` tools allow your crew to audit the health of your entire stack. If one agent encounters a failure, the crew can investigate the root cause. It turns your monitoring into an active investigation process. Your agents act as the first line of defense for your production infrastructure.

Setup guide

Set up New Relic AI (LLM Observability) MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke New Relic AI (LLM Observability) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="New Relic AI (LLM Observability) Analyst",
    goal="Access and analyze New Relic AI (LLM Observability) data via MCP.",
    backstory="Expert analyst with direct New Relic AI (LLM Observability) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent New Relic AI (LLM Observability) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="New Relic AI (LLM Observability) Analyst",
        goal="Access and analyze New Relic AI (LLM Observability) data via MCP.",
        backstory="Expert analyst with direct New Relic AI (LLM Observability) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent New Relic AI (LLM Observability) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by New Relic AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect New Relic AI (LLM Observability) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about New Relic AI (LLM Observability) MCP in CrewAI

They can. By adding this server to your agent definition, you enable them to query their own performance. It allows for autonomous optimization of your multi-agent team.

You give the monitoring agent access to the tools, while the worker agents focus on tasks. The monitor agent then reports back to the manager with actionable insights.

It does. You can program a crew member to monitor `query_llm_costs` and halt non-essential research tasks if budget limits are hit. It provides a safety net for your operations.

Your telemetry data is isolated within the Vinkius sandbox. Only the tools you explicitly expose to your agents can read the performance metrics.

You define the tools in the agent's configuration. The agent selects the right one based on the task description you provide in the crew setup.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python